MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation
This addresses the need for better portrait generation in computer vision, but appears incremental as it builds on existing diffusion control methods.
The paper tackles the problem of generating high-fidelity personalized portrait images by proposing MegaPortrait, a system that improves identity preservation and image fidelity compared to state-of-the-art AI portrait products.
We propose MegaPortrait. It's an innovative system for creating personalized portrait images in computer vision. It has three modules: Identity Net, Shading Net, and Harmonization Net. Identity Net generates learned identity using a customized model fine-tuned with source images. Shading Net re-renders portraits using extracted representations. Harmonization Net fuses pasted faces and the reference image's body for coherent results. Our approach with off-the-shelf Controlnets is better than state-of-the-art AI portrait products in identity preservation and image fidelity. MegaPortrait has a simple but effective design and we compare it with other methods and products to show its superiority.